© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17027
    Prev
    Next
    INDEX
    Explanations

    phrases related to inventories and allocation of resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various inventories and records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.70
    iasis
    -0.69
     PNG
    -0.65
    awar
    -0.65
     Abbas
    -0.62
    slow
    -0.62
    Wall
    -0.60
     underwear
    -0.60
    iban
    -0.60
     Whe
    -0.58
    POSITIVE LOGITS
    arbon
    0.84
    rarily
    0.81
    MpServer
    0.79
    poons
    0.75
    ynt
    0.73
    ettings
    0.72
    tesy
    0.72
    mith
    0.72
    æ©
    0.72
    ĸļ
    0.71
    Activations Density 0.121%

    No Known Activations